Parallel feature extraction and heterogeneous object-detection for multi-camera driver assistance systems

We present a flexible architecture for image-based feature detection and object classification on an FPGA. This architecture is tailored to the requirements of future driver assistance systems, which will make it necessary to detect a wide range of different object types in multi-camera systems requiring highly efficient hardware. In contrast to other designs, which typically address a specific object type or only accelerate early processing steps, the proposed pipeline offers different operation modes to switch resources for either detection or classification speed. In addition, the architecture can incorporate heterogeneous processors for different feature types. The design is tailored to support any object detection system using weak features and cascaded classifiers. For evaluation, a classic Viola Jones Detector is implemented being fully compatible with OpenCV.